A 55-template prompt benchmark showing general LLMs can beat specialized graph LLMs and GNNs on node classification and link prediction, though the reported margins are inflated by test-set prompt selection.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
GraphICL: Unlocking Graph Learning Potential in LLMs through Structured Prompt Design
A 55-template prompt benchmark showing general LLMs can beat specialized graph LLMs and GNNs on node classification and link prediction, though the reported margins are inflated by test-set prompt selection.